AWS Korea held a press conference at its Seoul headquarters on the 16th to release the AI-Driven Development Methodology (AI-DLC) and the specification-based development tool Kiro, aiming to address pain points in current AI programming such as "fast code generation, low delivery efficiency, and high security risks." AWS stated that currently, 94% of enterprises have not achieved the expected results after introducing AI into software development because existing AI tools mainly focus on the coding stage, which only accounts for about 20% of the entire development process. AI-DLC integrates AI throughout the entire lifecycle of requirement design, development, testing, and operation, achieving simultaneous generation of code, requirement documents, design documents, and operation manuals through continuous verification, manual approval, and full-process traceability. AWS stated that several Korean companies have already achieved significant results: LG Electronics' MS division doubled its development efficiency, CJ Olive Young completed five MVPs for projects in three days, and the development cycle for a large B2B platform project was shortened from two weeks to one week. Simultaneously, AWS launched the development tool Kiro, which allows for the generation of requirement and design documents before code development, and integrates functions such as automated testing, security checks, and external system connectivity. AWS's test results show that, under the same model, Kiro's development costs can be reduced to one-sixth to one-tenth of those of similar tools.
